L. panamensis 20200103: Sample Estimation.

1 Annotation version: 20200103

1.1 Genome annotation with OrgDb/TxDb/OrganismDbi

The tritrypdb just released a new version. Let us make new annotation data from it.

## These functions take _forever_ the first time around.
devtools::load_all("~/scratch/git/EuPathDB")

## Loading EuPathDB

## Loading required package: GenomeInfoDbData

pan_entry <- get_eupath_entry("panamensis", webservice="tritrypdb")

## Found the following hits: Leishmania panamensis MHOM/COL/81/L13, Leishmania panamensis strain MHOM/PA/94/PSC-1, choosing the first.

## Using: Leishmania panamensis MHOM/COL/81/L13.

installedp <- get_eupath_pkgnames(pan_entry)$orgdb_installed
if (!isTRUE(installedp)) {
  pan_annot <- EuPathDB::make_eupath_orgdb(pan_entry, reinstall=TRUE,
                                           overwrite=TRUE)
}
pan_names <- get_eupath_pkgnames(pan_entry)
library(pan_names$orgdb, character=TRUE)

## Loading required package: AnnotationDbi

## Loading required package: stats4

## Loading required package: IRanges

## Loading required package: S4Vectors

## 
## Attaching package: 'S4Vectors'

## The following objects are masked from 'package:EuPathDB':
## 
##     first, rename

## The following object is masked from 'package:base':
## 
##     expand.grid

## 
## Attaching package: 'IRanges'

## The following objects are masked from 'package:EuPathDB':
## 
##     collapse, desc, slice

## 
## Attaching package: 'AnnotationDbi'

## The following object is masked from 'package:EuPathDB':
## 
##     select

## 

pan_db <- get0(pan_names$orgdb)
pan_db

## OrgDb object:
## | DBSCHEMAVERSION: 2.1
## | DBSCHEMA: NOSCHEMA_DB
## | ORGANISM: Leishmania panamensis MHOM/COL/81/L13
## | SPECIES: Leishmania panamensis MHOM/COL/81/L13
## | CENTRALID: GID
## | Taxonomy ID: 1295824
## | Db type: OrgDb
## | Supporting package: AnnotationDbi

## 
## Please see: help('select') for usage information

For those packages I have generated/installed, use this to generate an annotation table. Oh, but I prefixed the column names with ‘annot_’ in order to make sure that nothing is duplicated with the GO tables, ortholog tables, etc.

But first, lets see what columns are available in the annotation packages.

all_fields <- columns(pan_db)
head(all_fields)

## [1] "ANNOT_BFD3_CDS"   "ANNOT_BFD3_MODEL" "ANNOT_BFD6_CDS"   "ANNOT_BFD6_MODEL"
## [5] "ANNOT_CDS"        "ANNOT_CDS_LENGTH"

all_lp_annot <- load_orgdb_annotations(
  pan_db,
  keytype="gid",
  fields="all")$genes

## Selecting the following fields, this might be too many: 
## ANNOT_BFD3_CDS, ANNOT_BFD3_MODEL, ANNOT_BFD6_CDS, ANNOT_BFD6_MODEL, ANNOT_CDS, ANNOT_CDS_LENGTH, ANNOT_CHROMOSOME, ANNOT_DIF_CDS, ANNOT_DIF_MODEL, ANNOT_EC_NUMBERS, ANNOT_EC_NUMBERS_DERIVED, ANNOT_EXON_COUNT, ANNOT_FC_BFD3_CDS, ANNOT_FC_BFD3_MODEL, ANNOT_FC_BFD6_CDS, ANNOT_FC_BFD6_MODEL, ANNOT_FC_DIF_CDS, ANNOT_FC_DIF_MODEL, ANNOT_FC_PF_CDS, ANNOT_FC_PF_MODEL, ANNOT_FIVE_PRIME_UTR_LENGTH, ANNOT_GENE_ENTREZ_ID, ANNOT_GENE_EXON_COUNT, ANNOT_GENE_HTS_NONCODING_SNPS, ANNOT_GENE_HTS_NONSYN_SYN_RATIO, ANNOT_GENE_HTS_NONSYNONYMOUS_SNPS, ANNOT_GENE_HTS_STOP_CODON_SNPS, ANNOT_GENE_HTS_SYNONYMOUS_SNPS, ANNOT_GENE_LOCATION_TEXT, ANNOT_GENE_NAME, ANNOT_GENE_ORTHOLOG_NUMBER, ANNOT_GENE_ORTHOMCL_NAME, ANNOT_GENE_PARALOG_NUMBER, ANNOT_GENE_PREVIOUS_IDS, ANNOT_GENE_PRODUCT, ANNOT_GENE_SOURCE_ID, ANNOT_GENE_TOTAL_HTS_SNPS, ANNOT_GENE_TRANSCRIPT_COUNT, ANNOT_GENE_TYPE, ANNOT_GO_COMPONENT, ANNOT_GO_FUNCTION, ANNOT_GO_ID_COMPONENT, ANNOT_GO_ID_FUNCTION, ANNOT_GO_ID_PROCESS, ANNOT_GO_PROCESS, ANNOT_HAS_MISSING_TRANSCRIPTS, ANNOT_INTERPRO_DESCRIPTION, ANNOT_INTERPRO_ID, ANNOT_IS_PSEUDO, ANNOT_ISOELECTRIC_POINT, ANNOT_LOCATION_TEXT, ANNOT_MATCHED_RESULT, ANNOT_MOLECULAR_WEIGHT, ANNOT_NO_TET_CDS, ANNOT_NO_TET_MODEL, ANNOT_ORGANISM, ANNOT_PF_CDS, ANNOT_PF_MODEL, ANNOT_PFAM_DESCRIPTION, ANNOT_PFAM_ID, ANNOT_PIRSF_DESCRIPTION, ANNOT_PIRSF_ID, ANNOT_PREDICTED_GO_COMPONENT, ANNOT_PREDICTED_GO_FUNCTION, ANNOT_PREDICTED_GO_ID_COMPONENT, ANNOT_PREDICTED_GO_ID_FUNCTION, ANNOT_PREDICTED_GO_ID_PROCESS, ANNOT_PREDICTED_GO_PROCESS, ANNOT_PROJECT_ID, ANNOT_PROSITEPROFILES_DESCRIPTION, ANNOT_PROSITEPROFILES_ID, ANNOT_PROTEIN_LENGTH, ANNOT_PROTEIN_SEQUENCE, ANNOT_SEQUENCE_ID, ANNOT_SIGNALP_PEPTIDE, ANNOT_SIGNALP_SCORES, ANNOT_SMART_DESCRIPTION, ANNOT_SMART_ID, ANNOT_SOURCE_ID, ANNOT_STRAND, ANNOT_SUPERFAMILY_DESCRIPTION, ANNOT_SUPERFAMILY_ID, ANNOT_THREE_PRIME_UTR_LENGTH, ANNOT_TIGRFAM_DESCRIPTION, ANNOT_TIGRFAM_ID, ANNOT_TM_COUNT, ANNOT_TRANS_FOUND_PER_GENE_INTERNAL, ANNOT_TRANSCRIPT_INDEX_PER_GENE, ANNOT_TRANSCRIPT_LENGTH, ANNOT_TRANSCRIPT_LINK, ANNOT_TRANSCRIPT_PRODUCT, ANNOT_TRANSCRIPT_SEQUENCE, ANNOT_TRANSCRIPTS_FOUND_PER_GENE, ANNOT_UNIPROT_ID, ANNOT_URI, ANNOT_WDK_WEIGHT

## Extracted all gene ids.

## Attempting to select: ANNOT_BFD3_CDS, ANNOT_BFD3_MODEL, ANNOT_BFD6_CDS, ANNOT_BFD6_MODEL, ANNOT_CDS, ANNOT_CDS_LENGTH, ANNOT_CHROMOSOME, ANNOT_DIF_CDS, ANNOT_DIF_MODEL, ANNOT_EC_NUMBERS, ANNOT_EC_NUMBERS_DERIVED, ANNOT_EXON_COUNT, ANNOT_FC_BFD3_CDS, ANNOT_FC_BFD3_MODEL, ANNOT_FC_BFD6_CDS, ANNOT_FC_BFD6_MODEL, ANNOT_FC_DIF_CDS, ANNOT_FC_DIF_MODEL, ANNOT_FC_PF_CDS, ANNOT_FC_PF_MODEL, ANNOT_FIVE_PRIME_UTR_LENGTH, ANNOT_GENE_ENTREZ_ID, ANNOT_GENE_EXON_COUNT, ANNOT_GENE_HTS_NONCODING_SNPS, ANNOT_GENE_HTS_NONSYN_SYN_RATIO, ANNOT_GENE_HTS_NONSYNONYMOUS_SNPS, ANNOT_GENE_HTS_STOP_CODON_SNPS, ANNOT_GENE_HTS_SYNONYMOUS_SNPS, ANNOT_GENE_LOCATION_TEXT, ANNOT_GENE_NAME, ANNOT_GENE_ORTHOLOG_NUMBER, ANNOT_GENE_ORTHOMCL_NAME, ANNOT_GENE_PARALOG_NUMBER, ANNOT_GENE_PREVIOUS_IDS, ANNOT_GENE_PRODUCT, ANNOT_GENE_SOURCE_ID, ANNOT_GENE_TOTAL_HTS_SNPS, ANNOT_GENE_TRANSCRIPT_COUNT, ANNOT_GENE_TYPE, ANNOT_GO_COMPONENT, ANNOT_GO_FUNCTION, ANNOT_GO_ID_COMPONENT, ANNOT_GO_ID_FUNCTION, ANNOT_GO_ID_PROCESS, ANNOT_GO_PROCESS, ANNOT_HAS_MISSING_TRANSCRIPTS, ANNOT_INTERPRO_DESCRIPTION, ANNOT_INTERPRO_ID, ANNOT_IS_PSEUDO, ANNOT_ISOELECTRIC_POINT, ANNOT_LOCATION_TEXT, ANNOT_MATCHED_RESULT, ANNOT_MOLECULAR_WEIGHT, ANNOT_NO_TET_CDS, ANNOT_NO_TET_MODEL, ANNOT_ORGANISM, ANNOT_PF_CDS, ANNOT_PF_MODEL, ANNOT_PFAM_DESCRIPTION, ANNOT_PFAM_ID, ANNOT_PIRSF_DESCRIPTION, ANNOT_PIRSF_ID, ANNOT_PREDICTED_GO_COMPONENT, ANNOT_PREDICTED_GO_FUNCTION, ANNOT_PREDICTED_GO_ID_COMPONENT, ANNOT_PREDICTED_GO_ID_FUNCTION, ANNOT_PREDICTED_GO_ID_PROCESS, ANNOT_PREDICTED_GO_PROCESS, ANNOT_PROJECT_ID, ANNOT_PROSITEPROFILES_DESCRIPTION, ANNOT_PROSITEPROFILES_ID, ANNOT_PROTEIN_LENGTH, ANNOT_PROTEIN_SEQUENCE, ANNOT_SEQUENCE_ID, ANNOT_SIGNALP_PEPTIDE, ANNOT_SIGNALP_SCORES, ANNOT_SMART_DESCRIPTION, ANNOT_SMART_ID, ANNOT_SOURCE_ID, ANNOT_STRAND, ANNOT_SUPERFAMILY_DESCRIPTION, ANNOT_SUPERFAMILY_ID, ANNOT_THREE_PRIME_UTR_LENGTH, ANNOT_TIGRFAM_DESCRIPTION, ANNOT_TIGRFAM_ID, ANNOT_TM_COUNT, ANNOT_TRANS_FOUND_PER_GENE_INTERNAL, ANNOT_TRANSCRIPT_INDEX_PER_GENE, ANNOT_TRANSCRIPT_LENGTH, ANNOT_TRANSCRIPT_LINK, ANNOT_TRANSCRIPT_PRODUCT, ANNOT_TRANSCRIPT_SEQUENCE, ANNOT_TRANSCRIPTS_FOUND_PER_GENE, ANNOT_UNIPROT_ID, ANNOT_URI, ANNOT_WDK_WEIGHT

## 'select()' returned 1:1 mapping between keys and columns

hs_annot <- load_biomart_annotations()

## The biomart annotations file already exists, loading from it.

hs_annot <- hs_annot[["annotation"]]
hs_annot[["transcript"]] <- paste0(rownames(hs_annot), ".", hs_annot[["version"]])
rownames(hs_annot) <- make.names(hs_annot[["ensembl_gene_id"]], unique=TRUE)
tx_gene_map <- hs_annot[, c("transcript", "ensembl_gene_id")]

orthos <- EuPathDB::extract_eupath_orthologs(db=pan_db)

## Some columns were missing: ORTHOLOGS_COUNT

## Removing them, which may end badly.

## 'select()' returned 1:many mapping between keys and columns

## There are 52 possible species in this group.

## Found species: Blechomonas ayalai B08-376

## Found species: Bodo saltans strain Lake Konstanz

## Found species: Crithidia fasciculata strain Cf-Cl

## Found species: Endotrypanum monterogeii strain LV88

## Found species: Leishmania aethiopica L147

## Found species: Leishmania amazonensis MHOM/BR/71973/M2269

## Found species: Leishmania arabica strain LEM1108

## Found species: Leishmania braziliensis MHOM/BR/75/M2903

## Found species: Leishmania braziliensis MHOM/BR/75/M2904

## Found species: Leishmania braziliensis MHOM/BR/75/M2904 2019

## Found species: Leishmania donovani BPK282A1

## Found species: Leishmania donovani CL-SL

## Found species: Leishmania donovani strain LV9

## Found species: Leishmania enriettii strain LEM3045

## Found species: Leishmania gerbilli strain LEM452

## Found species: Leishmania infantum JPCM5

## Found species: Leishmania major strain Friedlin

## Found species: Leishmania major strain LV39c5

## Found species: Leishmania major strain SD 75.1

## Found species: Leishmania mexicana MHOM/GT/2001/U1103

## Found species: Leishmania panamensis MHOM/COL/81/L13

## Found species: Leishmania panamensis strain MHOM/PA/94/PSC-1

## Found species: Leishmania sp. MAR LEM2494

## Found species: Leishmania tarentolae Parrot-TarII

## Found species: Leishmania tropica L590

## Found species: Leishmania turanica strain LEM423

## Found species: Leptomonas pyrrhocoris H10

## Found species: Leptomonas seymouri ATCC 30220

## Found species: Paratrypanosoma confusum CUL13

## Found species: Trypanosoma brucei brucei TREU927

## Found species: Trypanosoma brucei gambiense DAL972

## Found species: Trypanosoma brucei Lister strain 427

## Found species: Trypanosoma brucei Lister strain 427 2018

## Found species: Trypanosoma congolense IL3000

## Found species: Trypanosoma congolense IL3000 2019

## Found species: Trypanosoma cruzi Brazil A4

## Found species: Trypanosoma cruzi CL Brener Esmeraldo-like

## Found species: Trypanosoma cruzi CL Brener Non-Esmeraldo-like

## Found species: Trypanosoma cruzi Dm28c 2014

## Found species: Trypanosoma cruzi Dm28c 2017

## Found species: Trypanosoma cruzi Dm28c 2018

## Found species: Trypanosoma cruzi marinkellei strain B7

## Found species: Trypanosoma cruzi strain CL Brener

## Found species: Trypanosoma cruzi Sylvio X10/1

## Found species: Trypanosoma cruzi Sylvio X10/1-2012

## Found species: Trypanosoma cruzi TCC

## Found species: Trypanosoma cruzi Y C6

## Found species: Trypanosoma evansi strain STIB 805

## Found species: Trypanosoma grayi ANR4

## Found species: Trypanosoma rangeli SC58

## Found species: Trypanosoma theileri isolate Edinburgh

## Found species: Trypanosoma vivax Y486

dim(orthos)

## [1] 530405      5

2 Sample Estimation

2.1 Generate expressionsets

tmrc3_hs_expt <- create_expt("sample_sheets/tmrc3_samples_20200102.xlsx",
                             file_column="hg3891hisatfile",
                             gene_info=hs_annot)

## Reading the sample metadata.

## The sample definitions comprises: 49 rows(samples) and 74 columns(metadata fields).

## Reading count tables.

## Reading count tables with read.table().

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30001/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30002/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30003/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30004/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30005/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30006/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30007/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30008/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30009/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30010/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30011/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30012/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30013/outputs/hisat2_hg38_91/forward.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30016/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30017/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30018/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30019/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30014/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30021/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30029/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30020/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30038/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30039/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30023/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30025/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30022/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30026/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30030/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30031/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30032/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30024/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30040/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30033/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30037/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30027/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30028/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30034/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30035/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30036/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30044/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30041/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30042/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30043/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30045/outputs/hisat2_hg38_91/concatenated.count.xz contains 58307 rows and merges to 58307 rows.

## Finished reading count tables.

## Matched 58243 annotations and counts.

## Bringing together the count matrix and gene information.

## Some annotations were lost in merging, setting them to 'undefined'.

## The final expressionset has 58302 rows and 44 columns.

libsizes <- plot_libsize(tmrc3_hs_expt)

## The scale difference between the smallest and largest
## libraries is > 10. Assuming a log10 scale is better, set scale=FALSE if not.

libsizes$plot

## I think samples 7,10 should be removed at minimum, probably also 9,11
nonzero <- plot_nonzero(tmrc3_hs_expt)
nonzero$plot

box <- plot_boxplot(tmrc3_hs_expt)

## This data will benefit from being displayed on the log scale.

## If this is not desired, set scale='raw'

## Some entries are 0.  We are on log scale, adding 1 to the data.

## Changed 1641803 zero count features.

box

rownames(all_lp_annot) <- paste0("exon_", rownames(all_lp_annot), ".E1")

tmrc3_lp_expt <- create_expt("sample_sheets/tmrc3_samples_20200102.xlsx",
                             file_column="lpanamensisv36hisatfile",
                             gene_info=all_lp_annot)

## Reading the sample metadata.

## The sample definitions comprises: 49 rows(samples) and 74 columns(metadata fields).

## Reading count tables.

## Reading count tables with read.table().

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30001/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30002/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30003/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30004/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30005/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30006/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30007/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30008/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30009/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30010/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30015/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30011/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30012/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30013/outputs/hisat2_lpanamensis_v36/forward.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30016/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30017/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30018/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30019/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30014/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30021/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30029/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30020/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30038/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30039/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30023/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30025/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30022/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30026/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30030/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30031/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30032/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30024/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30040/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30033/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30037/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30027/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30028/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30034/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30035/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30036/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30044/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30041/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30042/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30043/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## /mnt/sshfs/cbcbsub/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/lpanamensis_tmrc_2019/preprocessing/tmrc30045/outputs/hisat2_lpanamensis_v36/concatenated.count.xz contains 8846 rows and merges to 8846 rows.

## Finished reading count tables.

## Matched 8778 annotations and counts.

## Bringing together the count matrix and gene information.

## Some annotations were lost in merging, setting them to 'undefined'.

## Warning in create_expt("sample_sheets/tmrc3_samples_20200102.xlsx", file_column
## = "lpanamensisv36hisatfile", : The following samples have no counts! TMRC30010

## The final expressionset has 8841 rows and 45 columns.

hs_valid <- subset_expt(tmrc3_hs_expt, coverage=3000000)

## Subsetting given a minimal number of counts/sample.

## There were 44, now there are 41 samples.

plot_libsize(hs_valid)$plot

lp_tmrc3_valid <- subset_expt(tmrc3_lp_expt, coverage=10000)

## Subsetting given a minimal number of counts/sample.

## There were 45, now there are 4 samples.

valid_write <- write_expt(hs_valid, excel=glue("excel/hs_valid-v{ver}.xlsx"))

## Writing the first sheet, containing a legend and some summary data.

## Writing the raw reads.

## Graphing the raw reads.

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Writing the normalized reads.

## Graphing the normalized reads.

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 12. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 28 rows containing missing values (geom_dotplot).

## Writing the median reads by factor.

all_norm <- normalize_expt(hs_valid, norm="quant", transform="log2", convert="cpm", batch=FALSE,
                           filter=TRUE)

## This function will replace the expt$expressionset slot with:

## log2(cpm(quant(cbcb(data))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: performing count filter with option: cbcb

## Removing 40537 low-count genes (17765 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 1239 values equal to 0, adding 1 to the matrix.

## Step 5: not doing batch correction.

all_pca <- plot_pca(all_norm)
all_pca$plot

knitr::kable(all_pca$table)

	sampleid	condition	batch	batch_int	colors	labels	PC1	PC2	pc_1	pc_2	pc_3	pc_4	pc_5	pc_6	pc_7	pc_8	pc_9	pc_10	pc_11	pc_12	pc_13	pc_14	pc_15	pc_16	pc_17	pc_18	pc_19	pc_20	pc_21	pc_22	pc_23	pc_24	pc_25	pc_26	pc_27	pc_28	pc_29	pc_30	pc_31	pc_32	pc_33	pc_34	pc_35	pc_36	pc_37	pc_38	pc_39	pc_40
tmrc30001	TMRC30001	PBMCs	41935	1	#1B9E77	TMRC30001	-0.0388	-0.1828	-0.0388	-0.1828	-0.0355	-0.2840	0.0235	0.1039	-0.0948	0.0569	-0.0446	0.1607	-0.0258	0.0409	-0.2124	0.3413	-0.0285	0.3064	0.1573	-0.1855	-0.1242	0.0841	0.0187	0.0684	0.1398	0.0856	-0.1151	-0.0369	-0.0634	-0.0969	-0.1620	-0.0214	-0.0330	0.0069	0.0145	0.0345	0.1245	0.1565	0.1244	0.1020	0.0967	-0.5502
tmrc30002	TMRC30002	PBMCs	41935	1	#1B9E77	TMRC30002	-0.0258	-0.1942	-0.0258	-0.1942	-0.0277	-0.2895	0.0270	-0.0427	0.0707	0.0119	-0.0049	0.0491	-0.1277	0.1518	0.0791	0.2741	0.0899	0.2120	-0.0197	0.0422	0.0556	-0.0109	0.0713	-0.1124	0.1281	-0.0503	-0.0385	0.0580	0.0116	-0.0105	0.0706	0.0152	0.0429	-0.0030	0.0277	-0.0721	-0.2969	-0.5564	-0.2358	-0.3684	0.0093	0.1396
tmrc30003	TMRC30003	PBMCs	41935	1	#1B9E77	TMRC30003	-0.0253	-0.1983	-0.0253	-0.1983	-0.0141	-0.3149	-0.0944	-0.1002	0.0676	0.0002	0.0506	0.0044	-0.1446	0.2118	0.1954	0.1679	0.1593	0.1283	-0.1263	0.1679	0.2211	0.0655	0.1110	-0.1988	0.0063	-0.0536	0.1276	0.0977	0.0377	0.0331	0.0305	-0.0426	0.0174	0.0326	-0.0528	0.0676	0.2201	0.4244	0.1075	0.2463	-0.0846	0.3693
tmrc30004	TMRC30004	PBMCs	41935	1	#1B9E77	TMRC30004	-0.0411	-0.1808	-0.0411	-0.1808	-0.0315	-0.2982	0.0404	0.1424	-0.0922	-0.0265	0.0112	0.0561	0.0998	-0.2002	-0.2045	-0.1302	-0.1947	-0.0955	0.1823	-0.1791	-0.2252	0.0167	-0.1138	0.1822	0.0007	0.0543	-0.1303	-0.0866	-0.1019	-0.0783	-0.0829	-0.0112	0.0513	-0.0053	-0.0030	0.0154	0.0656	0.0466	0.0007	-0.1107	-0.4668	0.4562
tmrc30005	TMRC30005	PBMCs	41935	1	#1B9E77	TMRC30005	-0.0350	-0.1989	-0.0350	-0.1989	0.0008	-0.3607	-0.0893	0.0635	-0.0660	-0.0339	0.0239	-0.0338	-0.0031	-0.0829	-0.0193	-0.2706	-0.1141	-0.2308	0.0075	0.0032	-0.0481	-0.0880	-0.0703	0.0635	-0.0922	0.0433	0.0063	-0.0297	-0.0376	0.0230	-0.0210	-0.0227	-0.0977	0.0324	-0.0398	-0.0154	-0.1223	-0.0573	-0.0502	0.2079	0.7169	0.1229
tmrc30006	TMRC30006	PBMCs	41935	1	#1B9E77	TMRC30006	-0.0252	-0.1976	-0.0252	-0.1976	-0.0059	-0.3278	-0.1281	0.0071	0.0241	-0.0537	0.0475	-0.1581	-0.0264	-0.0588	0.1637	-0.3186	-0.0168	-0.2698	-0.1678	0.1811	0.0854	-0.0397	-0.0078	-0.0645	-0.1425	0.0050	0.0634	0.0207	0.0616	0.1138	0.1155	0.0377	0.0519	-0.0450	0.0218	-0.0234	0.0190	-0.0335	0.0321	-0.1310	-0.3574	-0.5407
tmrc30008	TMRC30008	Monocytes	41935	1	#7570B3	TMRC30008	0.0006	-0.1631	0.0006	-0.1631	-0.1717	0.0912	0.1490	0.1583	0.0103	0.0646	-0.0819	0.1195	0.2254	-0.1238	-0.0580	0.0359	0.0089	-0.0779	0.1766	-0.0938	0.0369	-0.1956	0.0362	0.0249	0.2344	-0.2345	0.4381	0.0434	0.4490	-0.0559	0.3597	-0.0056	0.0862	-0.1118	0.0284	0.0502	0.0473	0.0672	0.0482	-0.0690	0.0724	-0.0066
tmrc30009	TMRC30009	Neutrophils	41955	2	#D95F02	TMRC30009	0.1913	0.2060	0.1913	0.2060	-0.0863	-0.0207	0.1505	0.2519	-0.0886	-0.0389	0.3384	-0.1540	-0.0036	0.1457	0.0424	-0.0053	-0.1466	0.2073	-0.1489	0.3299	-0.2263	-0.0732	-0.5142	-0.1129	0.2053	0.0378	0.0935	-0.0952	0.1400	0.0348	-0.1163	-0.0023	-0.0196	0.0077	-0.0217	0.0679	0.0306	-0.0174	0.0021	0.0127	0.0032	0.0078
tmrc30011	TMRC30011	Neutrophils	41961	3	#D95F02	TMRC30011	0.1914	0.2299	0.1914	0.2299	-0.1050	-0.0430	0.0997	0.2852	-0.1842	-0.0889	0.3936	-0.2282	-0.1777	0.1822	-0.0032	0.0274	0.1793	-0.1192	0.0109	-0.3297	-0.0321	-0.1307	0.4161	0.1002	-0.1228	-0.2220	0.0748	-0.0067	-0.1756	0.0248	-0.0076	0.0138	0.0365	-0.0165	0.0841	0.0136	0.0159	0.0002	-0.0121	-0.0120	-0.0006	-0.0059
tmrc30012	TMRC30012	Monocytes	41962	4	#7570B3	TMRC30012	0.0027	-0.1341	0.0027	-0.1341	-0.1925	0.1493	0.2670	0.2643	0.0480	0.0175	0.0024	0.0429	0.2637	-0.0840	0.1769	0.0193	0.0578	0.0139	0.0242	0.1029	0.1889	0.1699	0.0520	0.0336	-0.1714	0.1522	-0.0890	0.0595	-0.0833	0.0377	-0.1153	-0.0098	-0.0354	0.1005	-0.0454	0.0465	0.0368	0.2258	-0.6307	-0.0727	0.0363	-0.0574
tmrc30013	TMRC30013	Monocytes	41963	5	#7570B3	TMRC30013	0.0080	-0.1357	0.0080	-0.1357	-0.1730	0.1334	0.2640	0.2741	0.0690	0.0003	-0.0276	-0.0666	0.2124	-0.1266	0.1585	0.0717	0.0280	0.0066	-0.0899	0.0592	0.2287	0.1461	0.0469	0.0126	-0.0807	0.0980	-0.1395	0.0365	-0.1176	0.0174	-0.0095	-0.0129	-0.0936	0.0596	-0.0440	-0.1305	-0.0573	-0.2811	0.6223	0.1362	-0.0102	0.0630
tmrc30016	TMRC30016	Biopsy	42096	6	#E7298A	TMRC30016	-0.2262	0.0941	-0.2262	0.0941	0.0347	-0.0054	-0.0858	0.0465	-0.2754	0.3537	-0.3119	-0.2974	0.1991	0.3897	-0.0297	-0.0062	0.0818	0.0329	0.0644	-0.0547	0.0203	0.1440	-0.1765	0.0367	-0.2089	-0.0817	0.0731	-0.1240	-0.0301	-0.0404	0.1045	0.3963	-0.0856	-0.0293	-0.0060	0.0593	-0.0377	-0.0218	-0.0065	0.0143	-0.0246	0.0333
tmrc30017	TMRC30017	Biopsy	42096	6	#E7298A	TMRC30017	-0.2426	0.1409	-0.2426	0.1409	0.0584	0.0314	-0.2157	0.1941	0.1232	-0.2534	-0.0514	0.1694	-0.0159	0.0255	-0.1130	-0.1019	0.2560	0.3491	0.0096	-0.0722	0.1115	-0.1528	-0.1560	0.1757	-0.3293	0.0299	0.0424	-0.2437	0.0994	0.2979	0.1131	-0.3155	-0.0491	0.0344	-0.0059	-0.0300	-0.0126	-0.0157	0.0237	-0.0450	-0.0201	0.0186
tmrc30018	TMRC30018	Biopsy	42186	7	#E7298A	TMRC30018	-0.2407	0.1575	-0.2407	0.1575	0.0283	0.1022	-0.3195	0.2636	0.1979	-0.2901	-0.1225	0.0298	-0.0466	0.1977	0.1486	0.3139	-0.3859	-0.2966	0.0869	0.0376	0.0898	-0.1925	-0.0345	0.0857	0.0728	0.0505	0.0603	0.1951	-0.0853	-0.1708	-0.0968	0.0609	-0.0709	0.0163	-0.0186	-0.0346	0.0416	-0.0047	-0.0204	-0.0097	-0.0336	-0.0098
tmrc30019	TMRC30019	Biopsy	42186	7	#E7298A	TMRC30019	-0.2417	0.1476	-0.2417	0.1476	0.0392	0.0208	-0.0945	0.1066	0.1066	-0.2397	0.0940	0.1722	0.0136	-0.1545	-0.0552	-0.1457	0.1155	-0.0236	-0.0744	-0.0178	-0.2252	0.5237	0.1025	-0.3020	0.1554	-0.3078	-0.0210	-0.0221	0.0562	-0.0838	0.0345	0.1727	-0.3245	0.0025	0.0232	-0.0205	-0.0462	0.0024	-0.0311	0.0227	0.0026	-0.0085
tmrc30014	TMRC30014	Monocytes	42264	8	#7570B3	TMRC30014	-0.0095	-0.1592	-0.0095	-0.1592	-0.1736	0.2121	-0.2497	-0.2128	-0.0967	-0.0663	0.1966	-0.1675	-0.0685	0.0349	0.0962	-0.1363	-0.1650	0.2211	0.2631	0.0322	-0.0221	0.1895	0.1002	0.2766	-0.0708	-0.0505	-0.1149	0.2692	0.3963	0.1106	-0.2120	0.0870	0.0519	0.1747	0.1438	0.0241	-0.0776	-0.0028	0.0779	-0.0375	0.0206	0.0199
tmrc30021	TMRC30021	Neutrophils	42264	8	#D95F02	TMRC30021	0.1805	0.1640	0.1805	0.1640	-0.0653	-0.0522	-0.1694	-0.1672	-0.0146	0.0106	-0.0344	0.0205	0.2787	-0.1210	0.1990	0.0439	-0.1546	0.2565	-0.0859	0.0497	-0.3317	-0.0168	0.1931	0.0316	-0.1400	0.1237	0.2866	-0.0045	-0.2060	-0.1492	0.1769	-0.0360	0.0339	0.0940	-0.0804	-0.3631	-0.2698	0.1779	0.0271	-0.0230	-0.0147	-0.0111
tmrc30029	TMRC30029	Eosinophils	42264	8	#66A61E	TMRC30029	0.1121	-0.0889	0.1121	-0.0889	0.3006	0.0981	-0.0775	-0.0818	-0.0254	-0.0603	0.1078	-0.1381	0.1252	-0.0991	0.2498	0.0429	-0.0827	0.1252	0.0889	-0.1744	0.0059	-0.0661	0.0618	-0.1601	-0.1494	-0.0006	-0.1462	-0.1657	0.1944	-0.1533	-0.0920	-0.0206	-0.0740	-0.5060	-0.3612	-0.0308	0.2582	-0.1313	-0.0598	0.0116	0.0329	0.0104
tmrc30020	TMRC30020	Biopsy	42187	9	#E7298A	TMRC30020	-0.2353	0.1121	-0.2353	0.1121	0.0340	-0.0077	0.1961	-0.2340	-0.3050	0.0398	-0.0585	-0.0767	0.0073	-0.0070	0.0311	-0.0216	0.0303	-0.0711	-0.1584	-0.1154	0.0882	0.0876	-0.2025	0.1005	0.0302	-0.2122	0.1236	0.3491	-0.0508	-0.1815	-0.1658	-0.5624	-0.1183	-0.0473	-0.0545	-0.0988	-0.0088	-0.0184	-0.0277	-0.0419	-0.0316	-0.0402
tmrc30039	TMRC30039	Neutrophils	42194	10	#D95F02	TMRC30039	0.1937	0.1722	0.1937	0.1722	-0.0692	-0.0898	0.0579	-0.1988	0.2365	-0.0083	-0.1011	0.0622	0.2136	0.0554	-0.0383	-0.1566	-0.3257	0.1918	0.0688	0.0125	0.1114	-0.0322	0.0486	-0.1166	-0.1427	-0.2494	-0.0216	0.0309	-0.2257	-0.0451	0.0709	-0.1000	-0.0288	0.0195	0.3313	0.4089	0.2419	-0.1911	-0.0134	0.0657	0.0246	-0.0235
tmrc30023	TMRC30023	Eosinophils	42194	10	#66A61E	TMRC30023	0.0885	-0.0865	0.0885	-0.0865	0.2542	0.0304	0.0887	-0.1180	0.2841	-0.2844	-0.1280	-0.6435	0.0537	-0.2083	-0.3037	0.1984	0.1458	0.0035	-0.0200	-0.0226	-0.0325	0.0172	-0.0467	0.0350	0.0723	0.0480	0.0721	0.0409	-0.0257	0.0124	0.0453	0.0097	-0.0214	0.1602	-0.0079	0.1264	-0.0814	0.0883	-0.0341	-0.0168	0.0246	-0.0020
tmrc30025	TMRC30025	Biopsy	42186	7	#E7298A	TMRC30025	-0.2338	0.1190	-0.2338	0.1190	0.0213	0.0002	0.2719	-0.2183	-0.1195	0.1035	-0.0149	-0.0632	-0.0411	0.0295	0.0231	0.0949	-0.2175	-0.1224	0.1089	0.1353	-0.0942	-0.2109	0.3141	-0.1136	0.0936	0.1462	-0.1212	-0.2892	0.1570	0.3050	0.0601	-0.1115	-0.4097	0.2015	0.0272	-0.0592	0.0706	0.0372	0.0022	-0.0525	-0.0427	0.0125
tmrc30022	TMRC30022	Biopsy	42187	9	#E7298A	TMRC30022	-0.2288	0.1172	-0.2288	0.1172	0.0316	-0.0260	0.3389	-0.2960	-0.1278	-0.2888	0.1404	0.2078	-0.1268	-0.1747	0.0166	-0.0500	0.0875	0.1214	-0.0332	0.0488	0.1729	-0.2155	-0.0701	0.1609	-0.0952	0.1481	0.1136	0.0440	-0.0672	-0.2113	-0.0091	0.5023	0.0222	-0.0648	0.0231	0.0752	-0.0119	0.0090	0.0343	0.0205	0.0050	-0.0130
tmrc30026	TMRC30026	Biopsy	42186	7	#E7298A	TMRC30026	-0.2215	0.1200	-0.2215	0.1200	0.0119	0.0323	0.1401	-0.0690	-0.1410	-0.1950	-0.0889	0.0116	0.0362	0.0272	0.0833	0.1425	-0.1124	-0.1422	-0.0402	-0.0080	-0.1794	0.2272	0.0326	-0.1458	-0.0342	0.0346	-0.1327	-0.0952	0.0222	0.2404	0.0994	-0.0835	0.7159	-0.0906	0.0270	0.0885	-0.0200	0.0017	0.0257	0.0712	0.1053	-0.0015
tmrc30030	TMRC30030	Monocytes	42264	8	#7570B3	TMRC30030	-0.0018	-0.1518	-0.0018	-0.1518	-0.1862	0.2402	-0.1764	0.0080	-0.1886	0.0575	-0.0442	-0.0133	-0.1511	-0.1794	-0.1876	0.0326	-0.1116	0.0987	-0.1894	-0.1365	-0.0379	-0.0995	-0.0611	-0.2494	0.0360	0.1580	0.0682	0.3101	-0.2655	0.4248	0.0901	0.1092	-0.1424	-0.3267	0.0926	0.0180	0.0479	0.0267	-0.0308	-0.0461	0.0118	0.0510
tmrc30031	TMRC30031	Neutrophils	42264	8	#D95F02	TMRC30031	0.1911	0.2072	0.1911	0.2072	-0.0835	-0.0290	-0.1883	0.0389	-0.2299	0.1006	-0.1567	0.0157	-0.1882	-0.4146	0.0560	0.2574	0.2700	-0.1369	0.2907	0.4117	-0.0250	-0.0576	-0.0709	0.0010	-0.1469	-0.1538	-0.2062	0.0053	-0.0083	-0.1073	0.0701	-0.0546	-0.0264	-0.0668	0.1177	0.0742	0.0026	0.0016	0.0097	0.0101	0.0088	0.0116
tmrc30032	TMRC30032	Eosinophils	42264	8	#66A61E	TMRC30032	0.1057	-0.0807	0.1057	-0.0807	0.2977	0.1775	-0.1873	0.1365	-0.3633	0.0731	0.0147	0.0928	-0.1220	-0.1709	-0.0809	-0.0352	-0.1956	0.0782	-0.2592	-0.0716	0.2678	0.0153	0.0659	-0.1166	0.0657	0.0018	0.0172	-0.1372	0.0174	-0.1809	0.1197	-0.0006	0.1246	0.5009	-0.1111	0.1237	0.0756	-0.0695	-0.0327	-0.0541	-0.0021	0.0029
tmrc30024	TMRC30024	Monocytes	42194	10	#7570B3	TMRC30024	0.0128	-0.1559	0.0128	-0.1559	-0.1789	0.1724	0.0402	-0.0296	0.0835	0.0351	-0.1801	0.0439	-0.1561	0.0350	-0.1580	-0.0152	0.0393	-0.0393	-0.1226	-0.0147	-0.1642	-0.2064	0.0634	-0.1868	-0.1748	-0.0714	0.1010	-0.1194	0.1535	-0.1460	-0.3063	-0.0182	0.0599	0.0475	0.0212	-0.0593	-0.1975	-0.1903	-0.1701	0.5515	-0.2209	-0.0273
tmrc30040	TMRC30040	Neutrophils	42194	10	#D95F02	TMRC30040	0.2064	0.2116	0.2064	0.2116	-0.0858	-0.0748	0.1000	-0.0648	0.1308	0.0348	-0.1467	0.0653	-0.1231	-0.0079	-0.1553	-0.1156	-0.1521	-0.0021	0.2205	-0.0787	0.3123	-0.0132	-0.0975	-0.1732	0.0343	-0.2830	-0.0509	-0.0040	-0.0328	0.2285	-0.2087	0.1323	0.1022	0.0496	-0.4359	-0.2138	-0.2101	0.1860	0.0648	-0.1337	0.0086	-0.0381
tmrc30033	TMRC30033	Eosinophils	42194	10	#66A61E	TMRC30033	0.1257	-0.0688	0.1257	-0.0688	0.3099	0.0731	0.1416	0.0739	0.0680	0.0409	-0.1505	0.0443	-0.1434	0.0644	-0.1215	-0.0760	-0.0413	0.0238	-0.0567	0.2090	-0.0152	0.0995	0.0490	0.1952	0.0107	-0.1215	0.0730	-0.0110	-0.0238	0.0647	-0.0772	0.0905	0.0980	-0.0830	0.3238	-0.5751	0.3827	-0.0438	-0.0596	-0.0364	0.0798	0.0362
tmrc30037	TMRC30037	Monocytes	42194	10	#7570B3	TMRC30037	0.0178	-0.1513	0.0178	-0.1513	-0.1785	0.1646	-0.0117	-0.1712	0.1237	-0.0159	-0.0219	0.0120	-0.0964	0.0749	0.2449	-0.0414	0.1171	-0.0135	-0.0935	-0.1330	-0.1987	-0.1428	-0.2095	0.2612	0.2301	-0.2655	-0.3423	-0.0496	-0.2025	0.0337	0.3509	0.0633	-0.0129	0.1784	-0.2200	-0.0698	0.1782	-0.0136	-0.0875	0.1377	-0.0102	-0.0509
tmrc30027	TMRC30027	Neutrophils	42194	10	#D95F02	TMRC30027	0.2035	0.2009	0.2035	0.2009	-0.0733	-0.0803	-0.1082	-0.1032	0.0414	0.0394	-0.2266	0.0777	-0.0370	-0.1113	0.2899	-0.0234	0.2194	-0.1315	-0.0133	-0.2373	-0.0294	0.1732	-0.0239	0.1447	0.2446	0.2791	0.3342	-0.1191	0.0353	0.2064	-0.3060	0.0525	-0.0233	0.0986	-0.0227	0.1483	0.2162	-0.2060	-0.0063	-0.0073	-0.0049	0.0215
tmrc30028	TMRC30028	Eosinophils	42194	10	#66A61E	TMRC30028	0.1280	-0.0872	0.1280	-0.0872	0.3199	0.0792	0.0231	0.0148	0.0082	0.0474	-0.0195	0.0927	0.0324	0.0115	0.3071	-0.0102	-0.0058	-0.0348	-0.0448	-0.1982	0.1227	-0.0754	-0.1292	0.0309	0.1912	-0.0734	-0.1477	-0.1734	-0.0130	0.0582	-0.0800	-0.0125	-0.0670	-0.1558	0.4559	0.0650	-0.4800	0.2713	0.0405	0.0398	-0.0502	-0.0024
tmrc30034	TMRC30034	Monocytes	42194	10	#7570B3	TMRC30034	0.0209	-0.1405	0.0209	-0.1405	-0.1865	0.1783	0.0407	-0.0424	0.1423	0.0241	-0.1594	0.0480	-0.1651	0.1373	-0.0109	-0.0805	0.0955	-0.0955	-0.2089	-0.0071	-0.2310	-0.0789	0.0117	-0.1230	-0.1980	0.0370	-0.0604	-0.1362	0.0311	-0.2788	-0.1884	-0.0424	0.0162	0.0090	0.0351	0.1434	0.0701	0.2167	0.2244	-0.5558	0.1843	0.0365
tmrc30035	TMRC30035	Neutrophils	42194	10	#D95F02	TMRC30035	0.2101	0.2350	0.2101	0.2350	-0.0933	-0.0582	0.0862	0.0224	0.0764	-0.0106	-0.1083	-0.0171	-0.2553	0.1575	-0.0929	-0.1595	-0.0291	-0.0266	0.0436	-0.1959	0.1041	0.1774	-0.0495	-0.0702	-0.0006	0.4595	-0.2200	0.1623	0.2602	-0.2482	0.3939	-0.0896	-0.0570	-0.0752	0.0727	-0.1128	-0.0361	0.0305	-0.0576	0.1046	-0.0295	0.0106
tmrc30036	TMRC30036	Eosinophils	42194	10	#66A61E	TMRC30036	0.1213	-0.0723	0.1213	-0.0723	0.3060	0.1188	0.1291	0.0960	0.0209	0.0653	-0.0913	0.1923	-0.1599	0.1917	-0.0702	-0.1271	-0.0267	-0.0029	0.0403	0.3038	-0.1912	0.1204	0.2202	0.3051	0.0199	0.0406	0.1058	0.1609	-0.1025	0.0926	0.0813	-0.0744	-0.0682	-0.1722	-0.3354	0.3683	-0.1968	-0.0251	0.0519	0.0508	-0.0613	-0.0171
tmrc30044	TMRC30044	Biopsy	42237	11	#E7298A	TMRC30044	-0.2533	0.1335	-0.2533	0.1335	0.0507	0.0343	-0.1238	0.1116	0.0565	0.1638	-0.0303	-0.1286	0.1549	-0.0109	-0.0179	-0.3847	0.2537	0.1758	0.1399	0.1309	0.0146	-0.2858	0.2213	-0.1510	0.4213	0.1474	-0.1617	0.1408	-0.1311	-0.1374	-0.1441	-0.0457	0.2235	-0.0209	0.0066	-0.0203	0.0308	0.0041	0.0148	0.0111	0.0179	0.0071
tmrc30041	TMRC30041	Monocytes	42264	8	#7570B3	TMRC30041	-0.0116	-0.1575	-0.0116	-0.1575	-0.1822	0.2128	-0.1584	-0.2367	0.0008	-0.0212	0.3000	-0.0106	-0.0135	0.1392	-0.2053	-0.0040	0.0219	-0.1612	0.2469	0.1486	0.2483	0.2183	-0.0592	0.0189	0.1526	0.1254	0.1994	-0.4169	-0.2871	-0.1379	0.0627	-0.1608	0.0269	-0.1514	0.0200	-0.0645	-0.0447	-0.0345	-0.0120	0.0053	-0.0066	-0.0269
tmrc30042	TMRC30042	Neutrophils	42264	8	#D95F02	TMRC30042	0.1664	0.1430	0.1664	0.1430	-0.0722	-0.0686	-0.1882	-0.1597	-0.0416	-0.0155	0.0861	0.1677	0.4306	0.1088	-0.3482	0.1465	0.1034	-0.1860	-0.4371	0.0972	0.1129	-0.0629	0.1149	0.2164	0.0856	-0.0001	-0.2706	0.0282	0.2066	0.0589	-0.0849	0.0730	-0.0167	-0.1145	-0.0404	-0.0044	-0.0152	0.0043	-0.0169	-0.0068	0.0004	0.0320
tmrc30043	TMRC30043	Eosinophils	42264	8	#66A61E	TMRC30043	0.1122	-0.0839	0.1122	-0.0839	0.2985	0.0896	0.0142	-0.1133	0.0297	0.0489	0.2550	0.2514	0.2249	0.1806	-0.0451	0.0620	0.2458	-0.2324	0.2939	-0.0900	-0.1646	-0.0929	-0.2057	-0.2975	-0.2007	0.1152	0.0220	0.2948	-0.0396	0.0961	0.0127	0.0197	0.0016	0.2800	0.0211	-0.0667	0.0606	-0.0668	0.0692	-0.0097	-0.0176	-0.0284
tmrc30045	TMRC30045	Biopsy	42258	12	#E7298A	TMRC30045	-0.2525	0.1584	-0.2525	0.1584	0.0741	-0.0112	-0.0237	-0.0037	0.4343	0.6019	0.3437	-0.0134	-0.1527	-0.2572	-0.0304	0.1432	-0.0991	-0.0408	-0.1350	-0.0875	-0.0016	0.0649	-0.0525	0.1331	-0.1298	0.0103	0.0338	0.0193	0.0468	-0.0016	0.0237	0.0207	0.1125	-0.0207	-0.0120	0.0460	-0.0141	0.0027	-0.0079	0.0181	0.0282	-0.0016

write.csv(all_pca$table, file="hs_donor_pca_coords.csv")
plot_corheat(all_norm)$plot

plot_topn(hs_valid)$plot

3 Questions from Najib

I wandered into Najib’s office and he asked a few interesting and pointed questions. I am not sure yet if I can properly address them with the samples at hand, let us look.

3.1 Individual cell types

Do we have samples sufficient to ask about individual cell types from visit 1 to visit 2?

hs_query <- hs_valid
pData(hs_query[["expressionset"]])[["cell_time"]] <- paste0(pData(hs_query)[["typeofcells"]], "_",
                                                            pData(hs_query)[["visitnumber"]])
hs_query <- set_expt_conditions(hs_query, fact="cell_time")
table(pData(hs_query)[["condition"]])

## 
##      Biopsy_1 Eosinophils_1 Eosinophils_2 Eosinophils_3   Monocytes_1 
##            10             3             2             2             3 
##   Monocytes_2   Monocytes_3 Neutrophils_1 Neutrophils_2 Neutrophils_3 
##             4             2             4             3             2 
##       PBMCs_1 
##             6

hs_query <- set_expt_batches(hs_query, fact="selectionmethod")

biopsy <- subset_expt(hs_query, subset="typeofcells=='Biopsy'")

## Using a subset expression.

## There were 41, now there are 10 samples.

biopsy_norm <- normalize_expt(biopsy, norm="quant", convert="cpm", filter=TRUE, transform="log2")

## This function will replace the expt$expressionset slot with:

## log2(cpm(quant(cbcb(data))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: performing count filter with option: cbcb

## Removing 42978 low-count genes (15324 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 40 values equal to 0, adding 1 to the matrix.

## Step 5: not doing batch correction.

plot_pca(biopsy_norm)$plot

eo <- subset_expt(hs_query, subset="typeofcells=='Eosinophils'")

## Using a subset expression.

## There were 41, now there are 7 samples.

eo_norm <- normalize_expt(eo, norm="quant", convert="cpm", filter=TRUE, transform="log2")

## This function will replace the expt$expressionset slot with:

## log2(cpm(quant(cbcb(data))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: performing count filter with option: cbcb

## Removing 46525 low-count genes (11777 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 9 values equal to 0, adding 1 to the matrix.

## Step 5: not doing batch correction.

plot_pca(eo_norm)$plot

neut <- subset_expt(hs_query, subset="typeofcells=='Neutrophils'")

## Using a subset expression.

## There were 41, now there are 9 samples.

neut_norm <- normalize_expt(neut, norm="quant", convert="cpm", filter=TRUE, transform="log2")

## This function will replace the expt$expressionset slot with:

## log2(cpm(quant(cbcb(data))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: performing count filter with option: cbcb

## Removing 48289 low-count genes (10013 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 4 values equal to 0, adding 1 to the matrix.

## Step 5: not doing batch correction.

plot_pca(neut_norm)$plot

mono <- subset_expt(hs_query, subset="typeofcells=='Monocytes'")

## Using a subset expression.

## There were 41, now there are 9 samples.

mono_norm <- normalize_expt(mono, norm="quant", convert="cpm", filter=TRUE, transform="log2")

## This function will replace the expt$expressionset slot with:

## log2(cpm(quant(cbcb(data))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: performing count filter with option: cbcb

## Removing 45926 low-count genes (12376 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 39 values equal to 0, adding 1 to the matrix.

## Step 5: not doing batch correction.

plot_pca(mono_norm)$plot

3.2 Can we get cell signatures?

hs_sig <- simple_xcell(hs_valid, column="cds_length")

## The biomart annotations file already exists, loading from it.

## xCell strongly perfers rpkm values, re-normalizing now.

## This function will replace the expt$expressionset slot with:

## rpkm(data)

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Filter is false, this should likely be set to something, good
##  choices include cbcb, kofa, pofa (anything but FALSE).  If you want this to
##  stay FALSE, keep in mind that if other normalizations are performed, then the
##  resulting libsizes are likely to be strange (potentially negative!)

## Leaving the data in its current base format, keep in mind that
##  some metrics are easier to see when the data is log2 transformed, but
##  EdgeR/DESeq do not accept transformed data.

## Leaving the data unnormalized.  This is necessary for DESeq, but
##  EdgeR/limma might benefit from normalization.  Good choices include quantile,
##  size-factor, tmm, etc.

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: not doing count filtering.

## Step 2: not normalizing the data.

## Step 3: converting the data with rpkm.

## Step 4: not transforming the data.

## Step 5: not doing batch correction.

## Loading required namespace: xCell

jet_colors <- grDevices::colorRampPalette(c("#00007F", "blue", "#007FFF", "cyan",
                                            "#7FFF7F", "yellow", "#FF7F00", "red", "#7F0000"))
tt <- hs_sig$xcell_result
heatmap.3(tt, trace="none", col=jet_colors, cexRow=0.5)

if (!isTRUE(get0("skip_load"))) {
  pander::pander(sessionInfo())
  message(paste0("This is hpgltools commit: ", get_git_commit()))
  message(paste0("Saving to ", savefile))
  tmp <- sm(saveme(filename=savefile))
}

## If you wish to reproduce this exact build of hpgltools, invoke the following:

## > git clone http://github.com/abelew/hpgltools.git

## > git reset defea68c4df789830e6d759243e1f973d2d9dca7

## This is hpgltools commit: Fri Dec 27 17:07:39 2019 -0500: defea68c4df789830e6d759243e1f973d2d9dca7

## Saving to 01_sample_estimation_v20200103.rda.xz

tmp <- loadme(filename=savefile)